notebook-lm

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.90). The SKILL.md and references/workflows.md explicitly show fetching and importing arbitrary public web content (client.sources.add_url, client.research.start/import_sources) and then using that notebook content for chat and artifact generation, so untrusted third-party pages can be ingested and materially influence actions.